红外图像实时增强的新算法

针对红外图像的特点,提出了一种红外图像实时增强的新算法。该算法通过分析图像的直方图,得到图像中目标像素数峰值的估计值,并作为平台直方图均衡化的阈值。用该阈值对直方图进行修正,然后通过修正后的直方图进行直方图均衡化。在FPGA内通过采用并行处理结构及流水线技术实现了该算法,并且每秒可处理25帧128×128×8bits的红外图像。理论分析和实验结果均表明,本算法克服了采用一般直方图均衡化增强红外图像的缺点?对背景和噪声增强过度,抑制了目标的增强。该算法对红外图像增强后,图像对比度是直方图均衡化增强后图像对比度的1.8倍。     

关于数字图像处理中直方图均衡化的探讨

直方图均衡化就是把一已知灰度概率分布的图像经过一种变换,使之演变成一幅具有均匀灰度概率分布的新图像。它是以累积分布函数变换法为基础的直方图修正法。分析和总结灰度直方图的均衡化算法并通过MATLAB实验验证该方法能有效达到图像增强的目的。     

基于多尺度Retinex算法的彩色雾霾图像增强研究

介绍了基于颜色恒常性理论的Retinex模型,并重点分析了色彩恢复多尺度Retinex(MSRCR)算法的原理和实现方法。为验证基于Retinex理论的算法对图像增强具有良好的效果,以雾霾天气采集到的3幅彩色道路监控图像为实验对象,在MATLAB7.0软件中,利用MSRCR算法、直方图均衡化2种图像增强方法,对实验图像进行去雾霾处理,并通过主观评价、图像信息熵、亮度通道直方图来比较和分析2种算法的图像增强效果。研究结果表明:采用MSRCR算法可以还原出细节更丰富、辨析度更高的画面,且处理后的图像具有更大的信息熵,图像色彩也更接近原始图像。     

模拟频域滤波重构直方图均衡的图像增强方法

针对传统图像增强方法的不足,提出一种基于模拟频域滤波重构直方图均衡的图像增强方法.将频率域滤波的思想引入空间域直方图运算当中,在模拟频率直方图统计中进行频率信息的统计,利用这些频率信息建立模拟频率域坐标,进行模拟频域滤波,对滤波处理后的直方图进行均衡化处理.实验表明:与传统方法相比,该算法优化了灰度级的动态分布范围,能得到更清晰的增强效果,且在图像中没有视觉明显的噪声放大.     

自适应红外图像直方图均衡增强算法

针对红外图像的特点,本文提出了一种自适应红外图像直方图均衡增强算法。该方法根据原始图像的直方图,自适应地构造出一个加权函数对原始图像的直方图进行加权处理,然后采用加权后的直方图对原始图像进行直方图均衡化。算法不需要人为指定阈值,而且克服了传统直方图均衡提升红外图像背景的缺点。实验结果表明,该算法对红外图像具有较好的增强效果,能够有效地抑制图像的背景,突出目标。     

自适应红外图像直方图均衡增强算法

针对红外图像的特点,本文提出了一种自适应红外图像直方图均衡增强算法.该方法根据原始图像的直方图,自适应地构造出一个加权函数对原始图像的直方图进行加权处理,然后采用加权后的直方图对原始图像进行直方图均衡化.算法不需要人为指定阈值,而且克服了传统直方图均衡提升红外图像背景的缺点.实验结果表明,该算法对红外图像具有较好的增强效果,能够有效地抑制图像的背景,突出目标.     

利用粗糙集和属性直方图的图像增强方法

利用粗糙集理论进行图像增强,子图的划分是关键。属性直方图是对直方图概念的推广,是一种由先验知识约束的直方图;将它用于子图的划分,在此基础上提出了一种基于粗糙集理论和属性直方图的图像增强方法。该方法利用属性直方图的 Otsu 算法确定灰度阈值,根据灰度阈值利用不可分辨关系,将图像划分为背景子图、目标子图和噪声子图,对去噪后背景子图和目标子图进行增强变换,并将它们合并得到增强图像。将该方法用于一种海底小目标图像增强。实验结果表明该方法处理增益为 11dB,明显地增强了图像,且不损害图像的边缘。该方法适用于图像有某种先验知识的场合。     

基于Retinex和同态滤波的X射线电池图像增强算法

针对工业X射线电池图像对比度低、视觉效果不好、不同区域处理效果差异大等问题,提出一种基于多尺度Retinex和同态滤波的X射线电池图像增强算法.首先利用多尺度Retinex算法中的高斯滤波对照射分量估计,从而得到反射分量.用改进的直方图均衡化方法来处理照射分量,采用改进的巴特沃斯高通滤波器对反射分量的局部细节增强.接着,将照射分量与反射分量按比例融合,最后用改进的同态滤波对图像增强,即可得到增强后的图像.采用客观评价的方法对算法的有效性进行评价,结果表明,所提的算法图像增强效果好且可以看到更多的细节.     

基于NETD的红外热像仪图像预处理方法研究

噪声等效温差(NETD)是红外热像仪的重要参数,它能够体现红外探测器的噪声特性。在剔除无效像元的基础上,利用线性滤波、非线性滤波、直方图均衡化和多尺度图像增强等算法对热像仪原始数据进行图像预处理;用实验者对画质和图像细节的直接观察作为定性判据,噪声等效温差作为定量判据,综合评价图像预处理算法的优劣。通过实验发现,线性滤波后进行多尺度图像增强的方式能够使图像细节更清晰,同时噪声等效温差减小约25.9%,是目前较为适合的实验用热像仪的图像预处理方式。     

基于RBF神经网络的低对比度图像自适应增强算法

针对低对比度图像增强问题,提出了一种将直方图修正与RBF神经网络相结合的图像对比度增强算法。首先由原始图像获得与其邻域存在对比度的像素的条件概率直方图,通过调整两个增强参数可以改变条件概率直方图和均匀分布直方图的权重,生成新的直方图对图像进行增强。采用RBF神经网络建立图像特征与两个增强参数之间的非线性映射关系。根据图像本身的特征快速获得增强参数,从而实现图像的自适应增强。该方法计算量小,实时性强,应用范围广,有较强的自适应性。     

Contrast enhancement using real coded genetic algorithm based modified histogram equalization for gray scale images

Histogram equalization is a well‐known technique used for contrast enhancement. The global HE usually results in excessive contrast enhancement because of lack of control on the level of contrast enhancement. A new technique named modified histogram equalization using real coded genetic algorithm (MHERCGA) is aimed to sweep over this drawback. The primary aim of this paper is to obtain an enhanced method which keeps the original brightness. This method incorporates a provision to have a control over the level of contrast enhancement and applicable for all types of image including low contrast MRI brain images. The basic idea of this technique is to partition the input image histogram into two subhistograms based on a threshold which is obtained using Otsu's optimality principle. Then, bicriteria optimization problem is formulated to satisfy the aforementioned requirements. The subhistograms are modified by selecting optimal contrast enhancement parameters. Finally, the union of the modified subhistograms produce a contrast enhanced and details preserved output image. While developing an optimization problem, real coded genetic algorithm is applied to determine the optimal value of contrast enhancement parameters. This mechanism enhances the contrast of the input image better than the existing contemporary HE methods. The quality of the enhanced brain image indicates that the image obtained after this method can be useful for efficient detection of brain cancer in further process like segmentation, classification, etc. The performance of the proposed method is well supported by the contrast enhancement quantitative metrics such as discrete entropy and natural image quality evaluator. © 2015 Wiley Periodicals, Inc. Int J Imaging Syst Technol, 25, 24–32, 2015     

Gaussian probability bi-histogram equalization for enhancement of the pathological features in medical images

In order to enhance the pathological features of medical images and aid the medical diagnosis, the image enhancement is a necessary process. This study presented the Gaussian probability model combining with bi-histogram equalization to enhance the contrast of pathological features in medical images. There are five different bi-histogram equalizations, namely, bi-histogram equalization (BBHE), dualistic sub-image histogram equalization (DSIHE), bi-histogram equalization with a plateau limit (BHEPL), bi-histogram equalization median plateau limit (BHEPL-D), and bi-histogram equalization with modified histogram bins (BHEMHB). The entropy, contrast, absolute mean brightness error (AMBE), and skewness difference are used to quantize the enhancement results. From the experimental result, it is observed that the entropy and contrast of the images can be effectively enhanced by using Gaussian probability bi-histogram equalizations, and the Gaussian probability bi-histogram equalization median plateau limit (GPBHEPL-D) has the best enhanced result. The proposed GPBHEPL-D method is effective in strengthening the pathological features in medical images, so as to increase the efficiency of doctors' diagnoses and computer-aided detection.     

Contrast enhancement dynamic histogram equalization for medical image processing application

Image processing requires an excellent image contrast‐enhancement technique to extract useful information invisible to the human or machine vision. Because of the histogram flattening, the widely used conventional histogram equalization image‐enhancing technique suffers from severe brightness changes, rendering it undesirable. Hence, we introduce a contrast‐enhancement dynamic histogram‐equalization algorithm method that generates better output image by preserving the input mean brightness without introducing the unfavorable side effects of checkerboard effect, artefacts, and washed‐out appearance. The first procedure of this technique is; normalizing input histogram and followed by smoothing process. Then, the break point detection process is done to divide the histogram into subhistograms before we can remap the gray level allocation. Lastly, the transformation function of each subhistogram is constructed independently. © 2011 Wiley Periodicals, Inc. Int J Imaging Syst Technol, 21, 280‐289, 2011;     

Image contrast enhancement with brightness preservation using an optimal gamma correction and weighted sum approach

The enhancement of image contrast and preservation of image brightness are two important but conflicting objectives in image restoration. Previous attempts based on linear histogram equalization had achieved contrast enhancement, but exact preservation of brightness was not accomplished. A new perspective is taken here to provide balanced performance of contrast enhancement and brightness preservation simultaneously by casting the quest of such solution to an optimization problem. Specifically, the non-linear gamma correction method is adopted to enhance the contrast, while a weighted sum approach is employed for brightness preservation. In addition, the efficient golden search algorithm is exploited to determine the required optimal parameters to produce the enhanced images. Experiments are conducted on natural colour images captured under various indoor, outdoor and illumination conditions. Results have shown that the proposed method outperforms currently available methods in contrast to enhancement and brightness preservation.     

一种基于视觉感兴趣区域的彩色图像增强方法

目的把视觉感兴趣区域概念引入直方图的建造中,提出了一种新的基于视觉感兴趣区域的图像增强方法,使增强效果更符合人眼视觉感知。方法首先在标准观测环境下利用先进的眼动仪设备获得人眼感兴趣区域,然后计算各子区域的平均显著值,以确定各个子区域的权重系数,最后采取类似直方图均衡化的思想,优化配比灰度级的动态范围。结果通过主客观实验结果表明,增强后的图像更符合人眼视觉感知。结论结合了视觉感知特性的直方图增强方法,弥补了传统直方图与人眼视觉感知不一致的弊端,其增强效果更佳。     

Adaptive contrast enhancement based on histogram modification framework

ABSTRACT

An adaptive contrast enhancement method is proposed in this paper. The proposed method is based on the contrast limited adaptive histogram equalization (CLAHE) and the histogram modification framework. The predefined clip point for the clipped histogram of each block in original CLAHE may still result in excessive contrast enhancement in homogeneous regions, which gives the enhanced image an unnatural look and creates visual artifacts. By replacing the clipped histogram with a modified histogram, the proposed method achieves success in adaptively enhancing contrast in each block based on its content. In addition to this, a novel mapping function is introduced to further improve the enhanced result of histogram equalization (HE). Experiments are conducted with both visible images and infrared images to evaluate the performance of the proposed method. The results show that the proposed method gets better performance on contrast enhancement and visual quality of the enhanced results.     

Medical image contrast enhancement based on improved sparrow search algorithm

The collection or transmission of medical images is often disturbed by various factors, such as insufficient brightness and noise pollution, which will result in the deterioration of image quality and significantly affect the clinical diagnosis. To improve the quality of medical images, a contrast enhancement method based on improved sparrow search algorithm is proposed in this paper. The method is divided into two steps to enhance the medical images. First, a new transform function is introduced to improve the brightness or contrast of medical images, and two parameters in the transform function are optimized by the improved sparrow search algorithm. Second, adaptive histogram equalization method with contrast limited is used to equalize the result image of the previous step to make the pixel distribution of the image more uniform. Finally, a large number of experiments and qualitative and quantitative analyses were conducted on the common data sets. The analysis results demonstrate that the presented approach outperforms some existing medical image processing approaches.